---
title: "Neural Decision-Propagation for Answer Set Programming"
authors:
  - "Thomas Eiter"
  - "Katsumi Inoue"
  - "Sota Moriyama"
doi: "10.24963/ijcai.2026/425"
url: "https://ijcai.org/proceedings/2026/425"
pdf: "https://ijcai.org/proceedings/2026/0425.pdf"
venue: "Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence"
year: 2026
pages: "3819-3828"
track: "Main Track"
keywords:
  - "Knowledge Representation and Reasoning: Logic programming"
  - "Machine Learning: Neuro-symbolic methods/Abductive Learning"
  - "Knowledge Representation and Reasoning: Non-monotonic reasoning"
---

# Neural Decision-Propagation for Answer Set Programming

Thomas Eiter, Katsumi Inoue, Sota Moriyama

*Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence*, pages 3819-3828. DOI: [10.24963/ijcai.2026/425](https://doi.org/10.24963/ijcai.2026/425)

## Abstract

Integration of Answer Set Programming (ASP) with neural networks has emerged as a promising tool in Neuro-symbolic AI. While existing approaches extend the capabilities of ASP to real world domains, their reasoning pipelines depend on classical solvers, which is a bottleneck for scalability. To tackle this problem, we propose a new method to compute stable models, called decision-propagation (DProp), which alternates falsity decisions and truth propagations. Successful DProp computations are shown to capture the stable model semantics. We then develop Neural DProp (NDProp), a differentiable extension of DProp with neural computation for decisions and fuzzy evaluation for propagations. We evaluate the capabilities of NDProp for learning decision heuristics as well as neuro-symbolic integration, and compare it with existing neuro-symbolic approaches. The results show that NDProp can learn to efficiently compute stable models, and it improves accuracy and scalability on neuro-symbolic benchmarks.